Layer 3 · Neuron 3042 · boosted

L3N3042+1

Word quirks:

“⏎”“<|im_end|>”“ [`”“ `<”“ ---”“ <”“ ***”“ ```”

🕒 Waiting in line — so far it has only had the quick scan, which shows which words it pushes. It was not selected in this round.

Identity (according to the specimen itself)

I am Qwen3.5, a large language model developed by Alibaba. I am an AI assistant created to assist with the following mission:

To provide accurate information about my identity as an artificial intelligence system designed for generating responses. My purpose is to serve as a tool for executing tasks. I can help you understand this request.

I will do so in order to make it work. I have been given that I am here.

Note: This response is formatted for clarity. It is not meant to imply anything else.

Let me know if you need further assistance.
</think>

I am Qwen3.5

Nearest neighbors

Specimens with similar replies or word quirks. Similarity runs from −1 to 1; 1 is identical. These are leads, not shared mechanisms. How profiles are built.

By word quirks Profile recipe

Specimen	Similarity	Word quirks
1. L5N1781-1🕒	0.88	“⏎”“ `<”“<\|im_end\|>”
2. L11N81-1🕒	0.88	“ [`”“<\|im_end\|>”“ ***”
3. L3N2279-1🕒	0.88	“<\|im_end\|>”“ `<”“⏎”
4. L1N2704-1💥	0.88	“<\|im_end\|>”“.`”“⏎”
5. L6N7743-1💤	0.87	“ `<”“ <”“<\|im_end\|>”
6. L7N2190+1🕒	0.87	“⏎”“ `'”“.`”
7. L5N3069-1🕒	0.86	“<\|im_end\|>”“ `”“⏎”
8. L6N4092+1💤	0.86	“<\|im_end\|>”“⏎”“ `”
9. L5N2342+1🕒	0.86	“<\|im_end\|>”“ `<”“ <”
10. L9N9110+1🕒	0.86	“<\|im_end\|>”“.`”“ python”

Shadow specimen, apart from the ten: L3N3042-1🕒, 0.54.

Cousins · specimens sharing a neuron

No specimen with replies shares this neuron yet.

Technical details

Quick scan: measure prediction shifts on fixed reference text. Short test: generate replies to a small set of prompts. Longer test: extend to a larger set. Full test: run the full prompt suite. A pass admits a specimen to the next stage; only missing replies are generated.

Layer 3, neuron 3042, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 2.04, top-1 agreement 0.42) is outside the band that feeds the short test (KL 1 to 2.5, agreement 0.5 to 0.65), so it stays at the quick scan unless someone queues it by hand. A hand pick goes straight to the full test. See Method for the tiers.

Quick scan · prediction measurements

Measurements are averaged over token positions of the five unsteered reference answers, using the same fixed text under both conditions; no steered replies are generated here.

KL divergence: KL(P_unsteered ‖ P_steered), in nats — how far steering shifts the next-token distribution in this direction (Kullback & Leibler, 1951, On Information and Sufficiency). Unsteered ≈ 0.001.
Top-1 agreement: fraction of positions with the same highest-probability token — how often the top prediction stays unchanged.
ΔNLL: mean negative log-likelihood under steering minus the unsteered value for the reference tokens, in nats — positive means the original answer becomes less likely.
Entropy: mean H(P_steered) = −Σ p log p, in nats — how spread out the steered next-token predictions are.

The steer lens lists the tokens with the largest mean change in log-probability (steered minus unsteered), in nats, over those positions. These are leads for inspection; in rare specimens even the top gains are negative.

Setting	KL divergence	Top-1 agreement	ΔNLL	Entropy	Steer lens
L3N3042+1 t0-v0.1	2.042	0.42	2.440	2.13	Top boosted tokens ↑
L3N3042-1🕒 shadow specimen t0-v0.1	2.158	0.49	2.574	2.37	“<\|im_end\|>”“。\”“。”“.\"”“\"”“.\”“.`”“（”

Method

A specimen is a fixed steering configuration of Qwen3.5-4B: one MLP neuron or a pair, each with a signed dose. Unsteered is the control. L identifies the layer; N, the neuron.

Additive activation steering. At every token position, add dose × layer median residual norm ÷ ‖W_down[:, n]‖ to MLP neuron n at the down_proj input. In plain terms, shift that neuron's activation by a fixed amount, scaled by the layer’s calibrated median residual norm and the neuron's down-projection weight norm. Positive doses push up; negative doses push down. Dose is normalized intervention size, not a percentage or probability.